# Ezra > Ezra is an AI employee that works inside Slack. A team connects the systems it > already uses, Ezra reads them through each person's existing permissions, and > does real work in the channel — reviews, research, drafts, memos — citing the > source behind every figure. He sends, posts or writes nothing without a human > clicking approve. Ezra is made by Strata Systems LLC and lives at https://tryezra.ai. ## What it does - **Works where the team already is.** No new app, no new login, no migration. Ezra joins the Slack channels he is invited to and answers in the thread, so the answer stays there for whoever looks later. - **Reads the systems the business runs on.** Google Drive, Gmail, Calendar, Notion, HubSpot, Airtable, Salesforce, QuickBooks, Dropbox, Linear and more, connected once for the whole workspace through OAuth. - **Cites its sources.** Every figure carries the document behind it, down to the tab. Anyone can check an answer without going back to the person who posted it. - **Stops before it sends.** Reads are not gated; writes always are. There is no setting that turns the approval gate off. - **Keeps going on a schedule.** Ask in a sentence and it becomes a standing order that runs until someone in the channel tells it to stop. ## What makes it different from a chat assistant A private chat starts from zero every time and nothing it produces is visible to the rest of the team. Ezra answers in the channel, from the workspace's connected systems, and the answer stays there for anyone who scrolls back. The differentiating claim is checkability rather than intelligence: work whose sources are shown, so it can be verified rather than trusted. ## Security posture - OAuth only. No passwords are stored. - Ezra never sees more than the person asking. He inherits each person's existing permissions; if they cannot open a file, neither can he. - Workspace content is not used to train any model, ours or a provider's. - Encrypted in transit and at rest. - An audit log of what Ezra read, when, and for whom, exportable by admins. - Data is deleted when a source is disconnected. - SOC 2 Type II is **in progress, not complete**. GDPR is supported. ## Pricing Usage-based, not per seat. Everyone in the workspace can use Ezra and there is one meter, which runs on what Ezra actually does. New workspaces start with $100 in credits and no card is required. ## Models Ezra runs on a choice of frontier models — every model on the list ran the same evaluation against real work before it was admitted. The workspace picks which one to use. ## Links - [Home](https://tryezra.ai): what Ezra does, how it works, pricing and FAQ - [Privacy policy](https://tryezra.ai/privacy): what is collected, who processes it, how long it is kept - [Terms of service](https://tryezra.ai/terms): the approval gate, what Ezra's output is and is not, billing - [Book a call](https://calendly.com/hello-ontara/30min): talk to the person who built it ## Contact hello@ontara.io